Related papers: Towards a Brazilian History Knowledge Graph
Knowledge graphs (KGs) of real-world facts about entities and their relationships are useful resources for a variety of natural language processing tasks. However, because knowledge graphs are typically incomplete, it is useful to perform…
As a research community grows, more and more papers are published each year. As a result there is increasing demand for improved methods for finding relevant papers, automatically understanding the key ideas and recommending potential…
Automatic reasoning about textual information is a challenging task in modern Natural Language Processing (NLP) systems. In this work we describe our proposal for representing and reasoning about Portuguese documents by means of Linked Data…
The ever-growing datasets published on Linked Open Data mainly contain encyclopedic information. However, there is a lack of quality structured and semantically annotated datasets extracted from unstructured real-time sources. In this…
This paper describes technological and methodological options to achieve interoperability in accessing electronic information resources, available in Internet, in the scope of Brazilian Digital Library in Science and Technology Project -…
This research aimed to identify indications of scientific literacy resulting from a didactic and investigative interaction with Google Trends Big Data software by first-year students from a high-school in Novo Hamburgo, Southern Brazil.…
With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling a compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this…
Commonsense question answering (QA) requires a model to grasp commonsense and factual knowledge to answer questions about world events. Many prior methods couple language modeling with knowledge graphs (KG). However, although a KG contains…
We present our results regarding the automatic construction of a knowledge graph from historical documents related to the Chilean dictatorship period (1973-1990). Our approach consists on using LLMs to automatically recognize entities and…
This work supports further development of language technology for the languages of Africa by providing a Wikidata-derived resource of name lists corresponding to common entity types (person, location, and organization). While we are not the…
The semantic linked data model is at the core of the Web due to its ability to model real world entities, connect them via relationships and provide context, which could help to transform data into information and information into…
Relation extraction task is a crucial and challenging aspect of Natural Language Processing. Several methods have surfaced as of late, exhibiting notable performance in addressing the task; however, most of these approaches rely on vast…
Graphs have become the best way we know of representing knowledge. The computing community has investigated and developed the support for managing graphs by means of digital technology. Graph databases and knowledge graphs surface as the…
We present an LDA approach to entity disambiguation. Each topic is associated with a Wikipedia article and topics generate either content words or entity mentions. Training such models is challenging because of the topic and vocabulary…
Data verbalisation is a task of great importance in the current field of natural language processing, as there is great benefit in the transformation of our abundant structured and semi-structured data into human-readable formats.…
Knowledge Graphs (KGs) often have two characteristics: heterogeneous graph structure and text-rich entity/relation information. Text-based KG embeddings can represent entities by encoding descriptions with pre-trained language models, but…
In January 2019, prompted by the Wikimedia Movement's 2030 strategic direction, the Research team at the Wikimedia Foundation identified the need to develop a knowledge gaps index -- a composite index to support the decision makers across…
We introduce a next-generation vandalism detection system for Wikidata, one of the largest open-source structured knowledge bases on the Web. Wikidata is highly complex: its items incorporate an ever-expanding universe of factual triples…
Emergency-relevant data comes in many varieties. It can be high volume and high velocity, and reaction times are critical, calling for efficient and powerful techniques for data analysis and management. Knowledge graphs represent data in a…
Question answering (QA) over knowledge graphs has gained significant momentum over the past five years due to the increasing availability of large knowledge graphs and the rising importance of question answering for user interaction.…